X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finternetvideoarchive.py;h=16a6f73c87e27d47d401c444aa02b80d5a6313b3;hb=c3afc93a69fbfbe7712278f7ad03d0369ac9f885;hp=5986459d6dfdf7358b7d7a2e4bc139a579a01265;hpb=06723d47c4f934542a626569045e489a09796975;p=youtube-dl diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 5986459d6..16a6f73c8 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,5 +1,4 @@ import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -19,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor): u'info_dict': { u'title': u'SKYFALL', u'description': u'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.', - u'duration': 156, + u'duration': 153, }, } @@ -43,9 +42,8 @@ class InternetVideoArchiveIE(InfoExtractor): video_id = query_dic['publishedid'][0] url = self._build_url(query) - flashconfiguration_xml = self._download_webpage(url, video_id, + flashconfiguration = self._download_xml(url, video_id, u'Downloading flash configuration') - flashconfiguration = xml.etree.ElementTree.fromstring(flashconfiguration_xml.encode('utf-8')) file_url = flashconfiguration.find('file').text file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx') # Replace some of the parameters in the query to get the best quality @@ -53,9 +51,8 @@ class InternetVideoArchiveIE(InfoExtractor): file_url = re.sub(r'(?<=\?)(.+)$', lambda m: self._clean_query(m.group()), file_url) - info_xml = self._download_webpage(file_url, video_id, + info = self._download_xml(file_url, video_id, u'Downloading video info') - info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) item = info.find('channel/item') def _bp(p): @@ -74,7 +71,7 @@ class InternetVideoArchiveIE(InfoExtractor): }) formats = sorted(formats, key=lambda f: f['bitrate']) - info = { + return { 'id': video_id, 'title': item.find('title').text, 'formats': formats, @@ -82,6 +79,3 @@ class InternetVideoArchiveIE(InfoExtractor): 'description': item.find('description').text, 'duration': int(attr['duration']), } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info